Model: GELU Model: 4 Layers, 2048 Neurons per Layer

Dataset: 80% C4 (Web Text) and 20% Python Code

Neuron 1617 in Layer 1

Load this data into an Interactive Neuroscope

See Documentation here

Transformer Lens Loading: HookedTransformer.from_pretrained('gelu-4l')

Text #0

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.9467. Min Act: -0.1700

Data Index: 283562 (C4 (Web Text))

Max Activating Token Index: 16

Text #1

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.9467. Min Act: -0.1700

Data Index: 659337 (C4 (Web Text))

Max Activating Token Index: 32

Text #2

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.9467. Min Act: -0.1700

Data Index: 1064162 (C4 (Web Text))

Max Activating Token Index: 918

Text #3

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8529. Min Act: -0.1700

Data Index: 107334 (C4 (Web Text))

Max Activating Token Index: 646

Text #4

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7903. Min Act: -0.1700

Data Index: 994801 (C4 (Web Text))

Max Activating Token Index: 74

Text #5

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 971478 (C4 (Web Text))

Max Activating Token Index: 569

Text #6

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.8216. Min Act: -0.1700

Data Index: 478206 (C4 (Web Text))

Max Activating Token Index: 94

Text #7

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1113900 (C4 (Web Text))

Max Activating Token Index: 813

Text #8

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 794372 (C4 (Web Text))

Max Activating Token Index: 289

Text #9

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 124210 (C4 (Web Text))

Max Activating Token Index: 9

Text #10

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7903. Min Act: -0.1700

Data Index: 1036670 (C4 (Web Text))

Max Activating Token Index: 765

Text #11

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 1155355 (C4 (Web Text))

Max Activating Token Index: 59

Text #12

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 379093 (C4 (Web Text))

Max Activating Token Index: 384

Text #13

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.6965. Min Act: -0.1700

Data Index: 576398 (C4 (Web Text))

Max Activating Token Index: 602

Text #14

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 613532 (C4 (Web Text))

Max Activating Token Index: 33

Text #15

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7278. Min Act: -0.1700

Data Index: 303517 (C4 (Web Text))

Max Activating Token Index: 564

Text #16

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7278. Min Act: -0.1700

Data Index: 1037729 (C4 (Web Text))

Max Activating Token Index: 1006

Text #17

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.6965. Min Act: -0.1700

Data Index: 413744 (C4 (Web Text))

Max Activating Token Index: 1021

Text #18

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.7591. Min Act: -0.1700

Data Index: 408923 (C4 (Web Text))

Max Activating Token Index: 888

Text #19

Max Range: 3.9467. Min Range: -3.9467

Max Act: 3.6965. Min Act: -0.1700

Data Index: 1180895 (C4 (Web Text))

Max Activating Token Index: 9